INDEX

Explanations

phrases related to resistance or opposition

oai_token-act-pair · gpt-3.5-turbo

phrases related to resistance or opposition

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nces

-0.86

FORE

-0.74

]}

-0.68

terday

-0.66

shire

-0.65

inction

-0.65

SEA

-0.64

ances

-0.64

foundland

-0.64

 Stab

-0.64

POSITIVE LOGITS

 envelope

0.87

 boundaries

0.86

 buttons

0.86

 agenda

0.78

 wedge

0.78

 agendas

0.75

 brakes

0.75

 harder

0.74

rollers

0.74

 farther

0.73

Activations Density 0.149%

phrases related to resistance or opposition

phrases related to resistance or opposition

No Comments

No Known Activations